Hugging Face's logo

mlfoundations-dev
/
multiple_samples_none_numina_aime

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
sedrickkeh commited on
Commit
bcc0c69
·
verified ·
1 Parent(s): 8417768

Training in progress, epoch 1

Browse files
Files changed (5) hide show
  1. model-00001-of-00004.safetensors +1 -1
  2. model-00002-of-00004.safetensors +1 -1
  3. model-00003-of-00004.safetensors +1 -1
  4. model-00004-of-00004.safetensors +1 -1
  5. trainer_log.jsonl +42 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7974697220db89903a1e52c85aabb493b91c08af8f790ddd35d8f451ccbca550
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2352ba1f5bfef592aeeb233de3f5a6720a7c6ea2470da7c7812fbabcf23a230e
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3dd315599590e0c1296335dfb37d73cee841438594f8b592761cc053c330db33
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f30507fde085b22c82af0eb907fa12af5c70a2e4aab516434209411d99043298
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6019b6da49b2642d2c8780c589d667b917457dfd9e5a4692ebe2ab05e7bb0568
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb1e041a92d2c4a7d5746f6ca073bdf6ff62c1265aec831599b8c742455ce46d
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:478df5a84c3c87b23bcaa9bb4bc05e15876992ce185ae028853ef14b1ff90bea
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a5fb9ceef6c59e69e662ddd9c8faab17f26a5dd85ef6ee3af92c36aa71ad5b0
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -45,3 +45,45 @@
45
  {"current_steps": 45, "total_steps": 126, "loss": 0.7368, "lr": 8.14840211594757e-06, "epoch": 1.0627450980392157, "percentage": 35.71, "elapsed_time": "0:23:54", "remaining_time": "0:43:01"}
46
  {"current_steps": 46, "total_steps": 126, "loss": 0.7976, "lr": 8.039209983943201e-06, "epoch": 1.0862745098039215, "percentage": 36.51, "elapsed_time": "0:24:22", "remaining_time": "0:42:23"}
47
  {"current_steps": 47, "total_steps": 126, "loss": 0.7109, "lr": 7.927668892097288e-06, "epoch": 1.1098039215686275, "percentage": 37.3, "elapsed_time": "0:24:45", "remaining_time": "0:41:37"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  {"current_steps": 45, "total_steps": 126, "loss": 0.7368, "lr": 8.14840211594757e-06, "epoch": 1.0627450980392157, "percentage": 35.71, "elapsed_time": "0:23:54", "remaining_time": "0:43:01"}
46
  {"current_steps": 46, "total_steps": 126, "loss": 0.7976, "lr": 8.039209983943201e-06, "epoch": 1.0862745098039215, "percentage": 36.51, "elapsed_time": "0:24:22", "remaining_time": "0:42:23"}
47
  {"current_steps": 47, "total_steps": 126, "loss": 0.7109, "lr": 7.927668892097288e-06, "epoch": 1.1098039215686275, "percentage": 37.3, "elapsed_time": "0:24:45", "remaining_time": "0:41:37"}
48
+ {"current_steps": 48, "total_steps": 126, "loss": 0.738, "lr": 7.81386504884782e-06, "epoch": 1.1333333333333333, "percentage": 38.1, "elapsed_time": "0:25:19", "remaining_time": "0:41:09"}
49
+ {"current_steps": 49, "total_steps": 126, "loss": 0.8267, "lr": 7.697886411479422e-06, "epoch": 1.156862745098039, "percentage": 38.89, "elapsed_time": "0:25:48", "remaining_time": "0:40:33"}
50
+ {"current_steps": 50, "total_steps": 126, "loss": 0.7993, "lr": 7.579822618142505e-06, "epoch": 1.1803921568627451, "percentage": 39.68, "elapsed_time": "0:26:20", "remaining_time": "0:40:01"}
51
+ {"current_steps": 51, "total_steps": 126, "loss": 0.8324, "lr": 7.459764918573264e-06, "epoch": 1.203921568627451, "percentage": 40.48, "elapsed_time": "0:26:52", "remaining_time": "0:39:31"}
52
+ {"current_steps": 52, "total_steps": 126, "loss": 0.73, "lr": 7.3378061035681415e-06, "epoch": 1.227450980392157, "percentage": 41.27, "elapsed_time": "0:27:20", "remaining_time": "0:38:54"}
53
+ {"current_steps": 53, "total_steps": 126, "loss": 0.7399, "lr": 7.2140404332671986e-06, "epoch": 1.2509803921568627, "percentage": 42.06, "elapsed_time": "0:27:48", "remaining_time": "0:38:17"}
54
+ {"current_steps": 54, "total_steps": 126, "loss": 0.8289, "lr": 7.088563564301874e-06, "epoch": 1.2745098039215685, "percentage": 42.86, "elapsed_time": "0:28:19", "remaining_time": "0:37:45"}
55
+ {"current_steps": 55, "total_steps": 126, "loss": 0.7455, "lr": 6.961472475863406e-06, "epoch": 1.2980392156862746, "percentage": 43.65, "elapsed_time": "0:28:57", "remaining_time": "0:37:23"}
56
+ {"current_steps": 56, "total_steps": 126, "loss": 0.6694, "lr": 6.832865394749065e-06, "epoch": 1.3215686274509804, "percentage": 44.44, "elapsed_time": "0:29:25", "remaining_time": "0:36:47"}
57
+ {"current_steps": 57, "total_steps": 126, "loss": 0.8093, "lr": 6.702841719444141e-06, "epoch": 1.3450980392156864, "percentage": 45.24, "elapsed_time": "0:29:58", "remaining_time": "0:36:17"}
58
+ {"current_steps": 58, "total_steps": 126, "loss": 0.7096, "lr": 6.571501943298335e-06, "epoch": 1.3686274509803922, "percentage": 46.03, "elapsed_time": "0:30:29", "remaining_time": "0:35:44"}
59
+ {"current_steps": 59, "total_steps": 126, "loss": 0.814, "lr": 6.4389475768559675e-06, "epoch": 1.392156862745098, "percentage": 46.83, "elapsed_time": "0:30:56", "remaining_time": "0:35:08"}
60
+ {"current_steps": 60, "total_steps": 126, "loss": 0.6618, "lr": 6.305281069399989e-06, "epoch": 1.415686274509804, "percentage": 47.62, "elapsed_time": "0:31:20", "remaining_time": "0:34:28"}
61
+ {"current_steps": 61, "total_steps": 126, "loss": 0.6929, "lr": 6.17060572977047e-06, "epoch": 1.4392156862745098, "percentage": 48.41, "elapsed_time": "0:31:52", "remaining_time": "0:33:57"}
62
+ {"current_steps": 62, "total_steps": 126, "loss": 0.7561, "lr": 6.035025646518747e-06, "epoch": 1.4627450980392158, "percentage": 49.21, "elapsed_time": "0:32:29", "remaining_time": "0:33:32"}
63
+ {"current_steps": 63, "total_steps": 126, "loss": 0.7797, "lr": 5.898645607458941e-06, "epoch": 1.4862745098039216, "percentage": 50.0, "elapsed_time": "0:32:58", "remaining_time": "0:32:58"}
64
+ {"current_steps": 64, "total_steps": 126, "loss": 0.7374, "lr": 5.761571018679025e-06, "epoch": 1.5098039215686274, "percentage": 50.79, "elapsed_time": "0:33:24", "remaining_time": "0:32:22"}
65
+ {"current_steps": 65, "total_steps": 126, "loss": 0.8136, "lr": 5.623907823074044e-06, "epoch": 1.5333333333333332, "percentage": 51.59, "elapsed_time": "0:34:01", "remaining_time": "0:31:55"}
66
+ {"current_steps": 66, "total_steps": 126, "loss": 0.7933, "lr": 5.48576241846443e-06, "epoch": 1.5568627450980392, "percentage": 52.38, "elapsed_time": "0:34:36", "remaining_time": "0:31:27"}
67
+ {"current_steps": 67, "total_steps": 126, "loss": 0.7209, "lr": 5.347241575362729e-06, "epoch": 1.5803921568627453, "percentage": 53.17, "elapsed_time": "0:35:09", "remaining_time": "0:30:57"}
68
+ {"current_steps": 68, "total_steps": 126, "loss": 0.7747, "lr": 5.208452354452275e-06, "epoch": 1.603921568627451, "percentage": 53.97, "elapsed_time": "0:35:44", "remaining_time": "0:30:29"}
69
+ {"current_steps": 69, "total_steps": 126, "loss": 0.7635, "lr": 5.069502023841576e-06, "epoch": 1.6274509803921569, "percentage": 54.76, "elapsed_time": "0:36:19", "remaining_time": "0:30:00"}
70
+ {"current_steps": 70, "total_steps": 126, "loss": 0.7707, "lr": 4.9304979761584256e-06, "epoch": 1.6509803921568627, "percentage": 55.56, "elapsed_time": "0:36:47", "remaining_time": "0:29:26"}
71
+ {"current_steps": 71, "total_steps": 126, "loss": 0.6827, "lr": 4.791547645547727e-06, "epoch": 1.6745098039215687, "percentage": 56.35, "elapsed_time": "0:37:16", "remaining_time": "0:28:52"}
72
+ {"current_steps": 72, "total_steps": 126, "loss": 0.7939, "lr": 4.652758424637271e-06, "epoch": 1.6980392156862745, "percentage": 57.14, "elapsed_time": "0:37:47", "remaining_time": "0:28:20"}
73
+ {"current_steps": 73, "total_steps": 126, "loss": 0.7367, "lr": 4.514237581535571e-06, "epoch": 1.7215686274509805, "percentage": 57.94, "elapsed_time": "0:38:16", "remaining_time": "0:27:47"}
74
+ {"current_steps": 74, "total_steps": 126, "loss": 0.6935, "lr": 4.3760921769259585e-06, "epoch": 1.7450980392156863, "percentage": 58.73, "elapsed_time": "0:38:45", "remaining_time": "0:27:14"}
75
+ {"current_steps": 75, "total_steps": 126, "loss": 0.7474, "lr": 4.2384289813209754e-06, "epoch": 1.768627450980392, "percentage": 59.52, "elapsed_time": "0:39:13", "remaining_time": "0:26:40"}
76
+ {"current_steps": 76, "total_steps": 126, "loss": 0.7357, "lr": 4.101354392541061e-06, "epoch": 1.792156862745098, "percentage": 60.32, "elapsed_time": "0:39:44", "remaining_time": "0:26:08"}
77
+ {"current_steps": 77, "total_steps": 126, "loss": 0.7329, "lr": 3.964974353481254e-06, "epoch": 1.815686274509804, "percentage": 61.11, "elapsed_time": "0:40:14", "remaining_time": "0:25:36"}
78
+ {"current_steps": 78, "total_steps": 126, "loss": 0.7294, "lr": 3.829394270229531e-06, "epoch": 1.83921568627451, "percentage": 61.9, "elapsed_time": "0:40:46", "remaining_time": "0:25:05"}
79
+ {"current_steps": 79, "total_steps": 126, "loss": 0.6419, "lr": 3.694718930600012e-06, "epoch": 1.8627450980392157, "percentage": 62.7, "elapsed_time": "0:41:20", "remaining_time": "0:24:35"}
80
+ {"current_steps": 80, "total_steps": 126, "loss": 0.789, "lr": 3.5610524231440324e-06, "epoch": 1.8862745098039215, "percentage": 63.49, "elapsed_time": "0:41:54", "remaining_time": "0:24:06"}
81
+ {"current_steps": 81, "total_steps": 126, "loss": 0.7499, "lr": 3.428498056701665e-06, "epoch": 1.9098039215686273, "percentage": 64.29, "elapsed_time": "0:42:22", "remaining_time": "0:23:32"}
82
+ {"current_steps": 82, "total_steps": 126, "loss": 0.7664, "lr": 3.2971582805558622e-06, "epoch": 1.9333333333333333, "percentage": 65.08, "elapsed_time": "0:42:54", "remaining_time": "0:23:01"}
83
+ {"current_steps": 83, "total_steps": 126, "loss": 0.7651, "lr": 3.167134605250938e-06, "epoch": 1.9568627450980394, "percentage": 65.87, "elapsed_time": "0:43:26", "remaining_time": "0:22:30"}
84
+ {"current_steps": 84, "total_steps": 126, "loss": 0.771, "lr": 3.0385275241365965e-06, "epoch": 1.9803921568627452, "percentage": 66.67, "elapsed_time": "0:44:03", "remaining_time": "0:22:01"}
85
+ {"current_steps": 85, "total_steps": 126, "loss": 1.2373, "lr": 2.9114364356981274e-06, "epoch": 2.007843137254902, "percentage": 67.46, "elapsed_time": "0:45:32", "remaining_time": "0:21:57"}
86
+ {"current_steps": 86, "total_steps": 126, "loss": 0.7255, "lr": 2.7859595667328027e-06, "epoch": 2.0313725490196077, "percentage": 68.25, "elapsed_time": "0:46:04", "remaining_time": "0:21:25"}
87
+ {"current_steps": 87, "total_steps": 126, "loss": 0.6407, "lr": 2.6621938964318593e-06, "epoch": 2.0549019607843135, "percentage": 69.05, "elapsed_time": "0:46:31", "remaining_time": "0:20:51"}
88
+ {"current_steps": 88, "total_steps": 126, "loss": 0.6874, "lr": 2.5402350814267364e-06, "epoch": 2.0784313725490198, "percentage": 69.84, "elapsed_time": "0:46:57", "remaining_time": "0:20:16"}
89
+ {"current_steps": 89, "total_steps": 126, "loss": 0.654, "lr": 2.4201773818574956e-06, "epoch": 2.1019607843137256, "percentage": 70.63, "elapsed_time": "0:47:28", "remaining_time": "0:19:44"}